Invariant Image Classification using Triple-Correlation-Based Neural Networks

IEEE Transactions on Neural Networks

Volumn 5, Issue 3, 1994, Pages 392-408

  Delopoulos, Anastasios ^a   Tirakis, Andreas ^a   Kollias, Stefanos ^a  

^a NATIONAL TECHNICAL UNIVERSITY OF ATHENS   (Greece)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CLASSIFICATION (OF INFORMATION); COMPUTER ARCHITECTURE; CORRELATION METHODS; IMAGE ANALYSIS; INVARIANCE; MATHEMATICAL MODELS; PATTERN RECOGNITION; SIGNAL DISTORTION;

INVARIANT IMAGE CLASSIFICATION; MULTILAYER PERCEPTRONS; PERCEPTRON THEORY; TRIPLE CORRELATION BASED NEURAL NETWORKS; TWO DIMENSIONAL GRAY SCALE IMAGES;

NEURAL NETWORKS;

EID: 0028430458     PISSN: 10459227     EISSN: 19410093     Source Type: Journal    
DOI: 10.1109/72.286911     Document Type: Article

References (35)

1. E. Bienestock and C. A. Von der Malsburg. “A neural network for the retrieval of superimposed connection patterns,” Europhysics Letters, vol. 3, pp. 1243-1249, 1987.
2. V. Chandran, and S. Elgar, “Shape discrimination using invariant features defined from higher-order spectra,” in Proc. of Intl. Conf. on Acoustics Speech and Signal Processing, vol. 5, Toronto, Canada, May 14-18, 1991, pp. 3105-3109.
3. V. Chandran, and S. Elgar, “Position, rotation, and scale invariant recognition of images using higher-order spectra,” in Proc. of Intl. Conf. on Acoustics Speech and Signal Processing, vol. 5, San Fransisco, CA, March 1992, pp. 213-216.
4. Y. Chauvin, “A Backpropagation algorithm with optimal use of the hidden units,” in Advances in Neural Information Processing Systems I, D. Tourentry, Ed. Palo Alto, CA: Morgan Kaufman, 1989.
5. A. V. Dandawate and G. B. Giannakis, “Ergodicity and asymptotic normality for cumulant estimators of nonstationary signals,” Proc. of 25th Conf. on Info. Sciences and Systems, The Johns Hopkins Univ., Baltimore, March 1991, pp. 976-983.
6. J. Denker et al., “Handwritten digit recognition: Applications of network chips and automatic learning,” IEEE Communications Magazine, pp. 41-46, 1989.
7. R. Duda and P. Hart, Pattern Classification and Scene Analysis. New York: John Wiley and Sons, 1973.
8. K. Fukushima, S. Miyake, and T. Ito, “Neocognitron: A neural model for a mechanism of visual pattern recognition,” IEEE Trans, on Sys. Man and Cyh., vol. 13, no. 5, pp. 826-834, 1983.
9. K. Fukushima, “Neocognitron: A hierarchical neural network capable of visual pattern recognition,” Neural Networks, vol. 1, pp. 119-130, 1988.
10. G. B. Giannakis, and M. K. Tsatsanis, “Signal detection and classification using matched filtering and higher-order statistics,” IEEE Trans, on Acoustics Speech and Signal Processing, pp. 1284-1296, 1990.
11. G. B. Giannakis, and M. K. Tsatsanis, “A unifying maximum-likelihood view of cumulant and polyspectral measures for non-Gaussian signal classification and estimation,” IEEE Trans, on Information Theory, vol. 38, pp. 386-406, 1992.
12. G. L. Giles and T. Maxwell, “Learning, invariance and generalization in higher-order neural networks,” Applied Optics, vol. 26, 1987.
13. G. L. Giles, R. D. Griffin, and T. Maxwell, “Encoding geometric invariances in higher-order neural networks.” Neural Information Processing Systems, American Institute of Physics Conference Proceedings, 1988.
14. S. J. Hanson, “Comparing biases for minimal network construction with Backpropagation,” in Advances in Neural Information Processing Systems /, D. Tourentry, Ed. Palo Alto, CA: Morgan Kaufman, 1989.
15. M. H. Hayes, “The reconstruction of a multidimensional sequence from the phase or magnitude of its Fourier transform,” IEEE Trans, on Acoustics, Speech and Signal Processing, vol. 30, no. 2, pp. 140-154, 1982.
16. R. Jacobs, “Increased rates of convergence through learning rate adaptation,” Neural Networks, vol. 1, no. 4, 1988.
17. A. Khotanzad and J. H. Lu, “Classification of invariant image representations using a neural network,” IEEE Trans, on ASSP. vol. 38, pp. 1028-1038, 1990.
18. S. Kollias and D. Anastassiou, “An adaptive least squares algorithm for the efficient training of artificial neural networks,” IEEE Trans, on Circuits and Systems, vol. 36, pp. 1092-1101, 1989.
19. S. Kollias, A. Stafylopatis, and A. Tirakis, “Performance of higher order neural networks in invariant recognition,” in Neural Networks: Advances and Applications. North Holland, 1991, pp. 79-108.
20. Y. LeCun, “Generalization and network design strategies,” in Connectionism in Perspective. Switzerland: North Holland, pp. 143-155, 1989.
21. Y. LeCun, “A theoretical framework for backpropagation,” in Proceedings of the 1988 Connectionist Models Summer School, CMU, Pittsburg, 1989, San Mateo, CA: Morgan Kaufman.
22. C. Von der Malsburg, “Pattern recognition by labelled graph matching,” Neural Networks, vol. 1, pp. 141-148, 1988
23. J. M. Mendel, “Tutorial in higher-order statistics (spectra) in signal processing and system theory: Theoretical results and some applications,” Proc. IEEE, vol. 79, pp. 278-305, 1991.
24. A. V. Oppenheim, and J. L. Lim, “Importance of phase in signals,” Proc. IEEE, vol. 69, pp. 529-541, 1981.
25. Y. H. Pao, Adaptive Pattern Recognition and Neural Networks. Reading, MA: Addison-Welsey, 1989.
26. A. Papoulis, Probability, Random Variables, and Stochastic Processes. Third Edition, McGraw-Hill International Editions, Electrical & Electronic Engineering Series, 1991, pp. 212-213.
27. M. B. Reid, L. Spirkovska, and E. Ochoa, “Rapid training of higher-order neural networks for invariant pattern recognition,” in Proc. Joint Int. Conf. on Neural Networks, Washington, D.C., June 1989.
28. M. B. Reid, L. Spirkovska, and E. Ochoa, “Simultaneous position, scale, and rotation invariant pattern classification using third-order neural networks,” The International Journal of Neural Networks, vol. 1, no. 3, July 1989.
29. D. Rumelhart, and J. McClelland, Eds., Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, MA: MIT Press, vol. 1, 1986.
30. M. K. Tsatsanis and G. B. Giannakis, “Object and texture classification using mathced filtering and higher-order statistics,” Proc. of 6th Workshop on Multidimensional Signal Processing, Monterey, CA, September 1989, pp. 32-33.
31. M. K. Tsatsanis, and G. B. Giannakis, “Translation, rotation and scaling invariant object and texture classification using polyspectra,” in Proc. of Soc. of Photo-Opt. Instr. Engr., Advanced Signal Processing Alg., Arch, and Implem., San Diego, CA, July 1990, vol. 1348, pp. 103-115.
32. M. K. Tsatsanis, and G. B. Giannakis, “Object and texture classification using higher-order statistics,” IEEE Trans, on Pattern Analysis and Machine Intelligence, vol. 14, pp. 733-750, 1992.
33. B. Widrow and R. Winter, “Neural nets for adaptive filtering and adaptive pattern recognition,” IEEE Computer, vol. 21, no. 3, pp. 25-39, 1988.
34. B. Yegnanarayana, D. K. Saikia, and T. R. Krishnan, “Significance of group delay functions in signal reconstruction from spectral magnitude or phase,” IEEE Trans, on ASSP, vol. 32, no. 3, pp. 610-622, 1984.
35. ANNIE, “Applications of Neural Networks to Industrial Pattern Recognition Problems,” Esprit Project 2092 Handbook, 1991.